C. Statistical Investigation

To look at program consequences into the IPV and you may pathways, the research exploited the use of good cutoff threshold placed on an ongoing system qualification list (PMT get) to identify therapy and you can evaluation communities. Thus, results are legitimate on the population in the threshold and you can manage not show a complete www.datingranking.net/hindu-dating delivery away from socioeconomic standing into the research organizations. Due to the fact a discontinuity is employed for the task of your treatment, we guarantee the new conditions that typically need keep to have a frequent regression discontinuity framework method to be legitimate within our investigation, as well as zero control within threshold otherwise knowledge of the brand new formula of the potential beneficiaries so you’re able to determine the qualifications condition. The latest official try from equilibrium ranging from research and you can medication teams is actually together with reported into newest shot when you look at the tables dos and step 3 (col. 10). About total concentrating on do so presented, the new PMT results ranged off ?step three.294 to 4.601 z-scores, through the review test, the newest PMT ratings consist of ?0.571 in order to 0.324 z-results, for the system qualification cutoff during the ?0.106 z-score ( fundamental departure = 0.32 ). six Homes were systematically sampled around the cutoff to have testing aim, together with ensuing properties throughout the cures attempt is inside 0.46 standard deviations of one’s cutoff, and all of evaluation property was in this 0.43 fundamental deviations of the cutoff. Considering the small tolerance of the delivery regarding tested homes to the fresh PMT score, a straightforward Performed was applied to evaluate new influences of your own program: eight

Control details used in the analysis incorporated private- and domestic-top signs and you will people-height fixed outcomes. 8 On personal top, we managed having ages (in many years) and you can evidence when it comes down to official degree of both lady and you may partner. 9 Further, during the analysis of complete decide to try, i handle if you are when you look at the a polygamous relationship (source group is actually nonpolygamous otherwise, having easy breakdown, a beneficial monogamous commitment). Household-top manage parameters included home proportions and also the PMT rating. ten We declaration the newest a style of every area signal parameters into the descriptive harmony and attrition dining tables; however, even as we include society-height repaired effects, this type of symptoms aren’t used in regression study (districts: East Mamprusi, Karaga, and you can Yendi regarding the North Region and Bongo and you will Garu Tempane regarding the Higher East Area). To evaluate differences by the nearest and dearest framework, we interact the new sign getting polygamous commitment towards therapy indicator, go out sign, and you may impact guess (performing a multiple communication label): 11

D. Attrition

Attrition over the panel period has potential to threaten the internal validity and generalizability of the findings. Overall attrition in our analytic sample is approximately 10%, slightly higher than the overall household sample rate of 6.6%, and does not vary significantly between treatment and comparison samples ( p -value = .35 using a simple t-test; Table 1). Further, we investigate whether the sample lost to follow-up differs significantly from our panel sample in terms of IPV outcomes, control variables, or pathway indicators (tables 2, 3). Column 7 shows the mean difference between the sample lost to follow-up in the treatment group, as compared with the same in the comparison group. Column 8 shows the p-value of this difference derived from a regression using treatment to predict the specific indicator, controlling for the PMT score and restricting to attritors. Table 2 shows that across 12 background characteristics and 14 pathway variables, only one is significant at the p < .05 level (there is a statistically significantly higher proportion of the treatment group lost to follow-up as compared with the comparison group in Bongo district). Table 3 shows that across 15 outcome indicators, the only ones to show evidence of differential attrition at p < .05 or lower are those measuring the frequency of sexual IPV (means of those lost to follow-up in the comparison group are slightly higher at .28 vs. the treatment group at .26). These results indicate that the potential for bias in overall findings due to attrition is low. Despite these promising results, we do find that women leaving our sample across both treatment arms differ in terms of background characteristics from those who remain in our sample (p-values shown in cols. 3 and 6). For example, women who leave the sample are generally younger, better educated, in monogamous partnerships (vs. polygamous), and live in smaller households. This may be reflective of rural-to-urban migration or other mobility patterns, although these differences are not generally observed for pathway variables, including indicators of economic standing.